Improving the identification of haploid maize seeds using convolutional neural networks

Abstract

A critical step toward the success of the doubled haploid (DH) technique is the haploid identification within induction crosses. The R1-nj marker is the principal mechanism employed in this task enabling the selection of haploids at the seed stage. Although it seems easy to identify haploid seeds, this task is performed manually by visual classification, which becomes an inefficient process in terms of time and labor. Also, differential phenotypic expression of the R1-nj marker results in high rates of false positives among haploid seeds. For the first time, an image-based convolutional neural network (CNN) was trained to identify true positives among putative haploid seeds. The experiment was conducted using 3,000 maize (Zea mays L.) seeds from induction crosses classified as haploid (1,000), diploid (1,000), and inhibited (1,000) class. Images were taken from each seed, and then seeds were planted in the field to confirm their ploidy. For putative haploids (R1-nj phenotype), the classification accuracy on average was 94.39%, 97.07% for the haploid class, and 91.71% for the diploid class. However, the CNN model was unable to distinguish true haploid seeds among the putative haploid class, which indicates that CNN did not recognize different patterns between them. Finally, we provided a highly accurate and trained CNN model to the scientific community to classify haploid maize seeds via R1-nj, which can support maize breeders to optimize DH pipelines, mainly for small breeding programs with limited resources.

Identification Method of Wheat Cultivars by Using a Convolutional Neural Network Combined with Images of Multiple Growth Periods of Wheat

“…Liu et al [8] constructed a deep convolutional neural network (DCNN) for a dataset of 12,435 images composed of the leaves of 14 apple varieties, and its classification accuracy reached 97.11%. Sabadin et al [9] provided the scientific community with a highly accurate and well-trained CNN model that can classify haploid maize seeds through the differential phenotypic expression of R1-nj gene markers. This model can classify haploid and diploid corn seeds.…”

Haploid identification in maize

“…It is suitable for commercial haploid sorting as it can handle big data and simplify multiple processes between image extraction and neural network classification into a single pipeline (Ubbens and Stavness, 2017). Three models using CNN for the same sorting objective have been proposed by independent researchers (Veeramani et al, 2018;Altuntaşet al, 2019;Sabadin et al, 2021). A DeepSort CNN (Veeramani et al, 2018) • NIR spectra: skNIR platform.…”

“…illustrated 96.8% accuracy and 91.6% sensitivity. Meanwhile, Altuntaşet al (2019) using seven CNN architectures achieved 94.2% accuracy and 94.6% sensitivity Sabadin et al (2021). trained the CNN model that resulted in 94.39% accuracy and 97.07% sensitivity.…”

Progress in the Application of CNN-Based Image Classification and Recognition in Whole Crop Growth Cycles

“…The classification network effectively screened seed phenotypes during breeding activities. Additionally, Sabadin et al [27] capitalized on the distinction between haploid and diploid maize seed images, employing an improved CNN model. This approach successfully identified haploid seeds, providing valuable assistance in maize breeding efforts.…”